© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5680
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and components of equations or expressions in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical expressions containing "theta"

    np_acts-logits-general · gemini-2.0-flash

    theta and degree symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Donald
    -0.68
     McKnight
    -0.67
     Kaz
    -0.62
     Cas
    -0.62
    Hunt
    -0.60
    ADF
    -0.59
    Donald
    -0.58
     Whitney
    -0.57
    Kaz
    -0.57
     Whit
    -0.56
    POSITIVE LOGITS
     θ
    0.95
    theta
    0.94
     theta
    0.87
     Terrell
    0.81
    θ
    0.80
    tagext
    0.76
     Arthur
    0.74
     Grady
    0.72
     ARTHUR
    0.71
    Arthur
    0.70
    Activations Density 0.705%

    No Known Activations